Understanding Perturbed Parameter Ensemble Sensitivities Using A Contrastive Learning Approach
An explainable contrastive learning model that maps 5 monthly cloud and radiation fields into a shared representation space and demonstrates that explainable representations of climate fields can attribute model differences to specific variables, regions, seasons, and physical parameters.
Da Fan, D. J. Gagne, G. Elsaesser et al.
· 0 citations